A Hybrid Method for Calculating the Chemical Composition of Steel with the Required Hardness after Cooling from the Austenitizing Temperature

Trzaska, Jacek; Sitek, Wojciech

doi:10.3390/ma17010097

Cited by 3 publications

(3 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The integration of artificial neural networks with various modeling techniques, such as mathematical modeling, computational intelligence, and artificial intelligence is a common practice. The amalgamation of different methods within a single model enables the exploration of a larger problem space and leads to a synergistic effect that utilizes the strengths of the individual methods [23,51]. Table 9 shows the chemical compositions determined when comparing the 42CrMo4 steel grade hardness with the DIN EN 10083-3 technical standard [49].…”

Section: Illustrative Example Of Model 4208 To Determine Restricted H...mentioning

confidence: 99%

“…Artificial neural networks (ANNs) are invaluable for practical applications as they overcome the hurdles associated with formulating mathematical models. Their ability to establish connections between studied variables without the need for explicit mathematical descriptions is a distinctive feature that enables ANNs to learn solutions to problems based on identified patterns from the given experimentally collected data [1,[23][24][25].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Hardenability Modeling: A Bayesian Optimization Approach to Tuning Hyperparameters for Neural Network Regression

Gemechu,

Sitek,

Batalha

2024

Applied Sciences

View full text Add to dashboard Cite

This study investigates the application of regression neural networks, particularly the fitrnet model, in predicting the hardness of steels. The experiments involve extensive tuning of hyperparameters using Bayesian optimization and employ 5-fold and 10-fold cross-validation schemes. The trained models are rigorously evaluated, and their performances are compared using various metrics, such as mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). The results provide valuable insights into the models’ effectiveness and their ability to generalize to unseen data. In particular, Model 4208 (8-85-141-1) emerges as the top performer with an impressive RMSE of 1.0790 and an R2 of 0.9900. The model, which was trained with different datasets for nearly 40 steel grades, enables the prediction of hardenability curves, but is limited to the range of the training dataset. The research paper contains an illustrative example that demonstrates the practical application of the developed model in determining the hardenability band for a specific steel grade and shows the effectiveness of the model in predicting and optimizing heat treatment results.

show abstract

Section: Illustrative Example Of Model 4208 To Determine Restricted H...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improving Hardenability Modeling: A Bayesian Optimization Approach to Tuning Hyperparameters for Neural Network Regression

Gemechu,

Sitek,

Batalha

2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…It is known that the chemical composition has a tremendously profound influence on the mechanical properties of steel, which can be either problematic or can be used to develop fire resistance, as indicated in [22]. A modern approach to establishing the chemical composition of steel is a hybrid method involving artificial neural networks (ANNs), presented in [23].…”

Section: Introductionmentioning

confidence: 99%

The Initial Assessment of the Possibility of Simulation Fire Standard Curve in the Electric Furnace with the Assessment of Chemical Composition Changes in Steel after Cooling Phase

Kubicka,

Szczecina,

Suckert

et al. 2024

Metals

View full text Add to dashboard Cite

The article focuses on analyzing changes in the chemical composition of steel samples after the cooling phase. A few distinct types of samples made of St3S steel were heated in an electric resistance furnace for 1 h. The temperature in the following minutes of the furnace work was programmed to reflect the standard fire curve defined in the Eurocode in the best possible way. The box-type electric furnace was used. There were three series of samples, and each of them was cooled down in diverse ways: (a) in the water, (b) in the polymer cooling medium AQUA-QUENCH® 320, and (c) in the furnace. After that, the chemical composition of diverse types of samples with various kinds of cooling was checked. This task was realized using a laser elementary analysis microscope with the EA-300 head. The investigation allowed the authors to draw the following conclusions: the electric furnace may be used to simulate an increase in temperature with fire duration according to standard fire curve only in the phase of fully developed fire situation; the EA-300 head for laser elementary analysis allows checking of the chemical composition of investigated elements very quickly (in a few seconds).

show abstract

Improving Hardenability Modeling: A Bayesian Optimization Approach to Tuning Hyperparameters for Neural Networks Regression

Gemechu,

Sitek,

Batalha

2024

Preprint

View full text Add to dashboard Cite

This study investigates the application of regression neural networks, in particular the fitrnet model, in predicting the hardness of steels. The experiments involve extensive tuning of hyperparameters using Bayesian optimization and employ 5-fold and 10-fold cross-validation schemes. The trained models are rigorously evaluated, and their performances are compared using various metrics such as mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). The results provide valuable insights into the effectiveness of the models and their ability to generalize to unseen data. In particular, Model 4208 (8-85-141-1) emerges as the top performer with an impressive RMSE of 1.0790 and an R² of 0.9900. The research paper contains an illustrative example that demonstrates the practical application of the developed model in determining the hardenability band for a specific steel grade and shows the effectiveness of the model in predicting and optimizing heat treatment results.

show abstract

A Hybrid Method for Calculating the Chemical Composition of Steel with the Required Hardness after Cooling from the Austenitizing Temperature

Cited by 3 publications

References 50 publications

Improving Hardenability Modeling: A Bayesian Optimization Approach to Tuning Hyperparameters for Neural Network Regression

Improving Hardenability Modeling: A Bayesian Optimization Approach to Tuning Hyperparameters for Neural Network Regression

The Initial Assessment of the Possibility of Simulation Fire Standard Curve in the Electric Furnace with the Assessment of Chemical Composition Changes in Steel after Cooling Phase

Improving Hardenability Modeling: A Bayesian Optimization Approach to Tuning Hyperparameters for Neural Networks Regression

Contact Info

Product

Resources

About